{"id":"W2337944562","doi":"10.1109/jstars.2016.2527242","title":"Extraction of Urban Areas From Polarimetric SAR Imagery","year":2016,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Space Agency","keywords":"Wishart distribution; Remote sensing; Synthetic aperture radar; Polarimetry; Computer science; Land cover; Radar imaging; Covariance matrix; Radar; Contextual image classification; Classifier (UML); Pattern recognition (psychology); Artificial intelligence; Geography; Scattering; Land use; Image (mathematics); Algorithm; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001740601,0.000116811,0.0002374509,0.0003014949,0.00004630192,0.00001806958,0.00006493761,0.0001234373,0.000006127917],"category_scores_gemma":[0.00007152612,0.00009045398,0.00004011693,0.0005758447,0.00004078674,0.00009302116,0.000007211964,0.0002158645,4.960198e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000548897,"about_ca_system_score_gemma":0.0000460447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009303055,"about_ca_topic_score_gemma":0.00002641138,"domain_scores_codex":[0.9990957,0.00001872892,0.0004817087,0.0001040646,0.0001663587,0.0001334567],"domain_scores_gemma":[0.9991769,0.0002201183,0.0001825178,0.0001491831,0.0002230111,0.00004822085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009144912,0.00001477793,0.0004807634,0.00001186961,0.00003479629,0.000003164595,0.00006503964,0.00001186449,0.2398835,0.00017562,0.0001410356,0.7591684],"study_design_scores_gemma":[0.00140796,0.00009158935,0.1861622,0.0007771383,0.0001461504,0.0002041273,0.0001254245,0.02323557,0.6110481,0.01189525,0.1643022,0.0006043916],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4239757,0.0003270738,0.5747327,0.0002041433,0.0001177875,0.00008731417,0.000006839406,0.00003984175,0.0005086381],"genre_scores_gemma":[0.5409781,0.000430778,0.4583639,0.00001588639,0.0001744852,3.258382e-8,0.000001635585,0.00001401663,0.00002118452],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7585641,"threshold_uncertainty_score":0.3688606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01428784075285431,"score_gpt":0.218605779486354,"score_spread":0.2043179387334997,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}